Only this pageAll pages
Powered by GitBook
1 of 75

Docs

Introduction

Loading...

World Market

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Technical Specs

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Testnet

World Fund

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Loading...

Economics

Loading...

Loading...

External Links

Introduction

World Market is an on-chain perpetual decentralized exchange where you can trade crypto, commodities, forex, stocks, or bonds with leverage using any on-chain asset.

Global markets have long been a key application for blockchain technology. Centralized exchanges (CEXs) gained popularity in the early 2010s by offering spot trading and easy access to global cryptocurrency markets. In 2014, BitMEX introduced Perpetual Futures, transforming the trading landscape. This innovation was quickly adopted by other CEXs and fueled market expansion over next few years. By 2020, DeFi gained momentum with perpetual futures decentralized exchanges (DEXs) offering trustless and permissionless trading. While these markets since then have evolved, they are still primarily focused on cryptocurrency assets with a limited expansion into real-world assets (RWAs), such as gold, silver, and very limited number of forex pairs.

In contrast, traditional non-blockchain markets, such as Contract For Differences (CFDs), offer access to over 18,000 assets, processing billions in daily trading volume. They also integrate blockchain-based assets faster than DeFi markets can onboard new blockchain assets. However, CFDs often have wider spreads and higher costs, leaving users at the mercy of brokers. Several emerging asset classes, such as precious metals, yield, prediction, time-based assets, and real estate, are being developed for on-chain perpetual futures. These assets, however, are often illiquid, posing a challenge in DeFi markets, just like every other emerging asset class.

With World Market, we aim to bridge this gap by offering CeFi-level liquidity and TradFi market offerings on-chain. B3X has been working on building a derivatives marketplace designed to integrate any asset class including traditional assets and emerging DeFi assets with deep liquidity, familiar features, and seamless UX. By doing so, B3X enables DeFi to compete directly with TradFi and CeFi, providing a truly decentralized, efficient, and scalable trading platform for the world.

CeFi Dominates with 100x Volume

CeFi volumes still overshadow DeFi by a staggering 100x, with platforms like Hyperliquid driving the majority of the activity. Despite years of innovation, DeFi remains far from closing this gap. The core issue lies in limited market offerings and insufficient liquidity on DeFi venues, which stifle growth and fail to attract serious traders.

We are seeing an upward growth in DEX to CEX volume since our inception of DeFi markets and yet, we have barely captured the surface.

To compete at this scale, DeFi must deliver more than incremental improvements — it needs transformative markets that can rival CeFi in depth, efficiency, and accessibility. The time for half-measures is over.

Perhaps, it may also be due to the fact, earlier it was difficult to build such CeFi markets on DeFi due to the absence of chains to deliver similar performance as needed — but that excuse is not valid anymore, as we are seeing several high-performance chains in development now delivering the required performance.

So, the best time to compete with CeFi is now.

About B3X

“Building a new foundation takes a Heraclitean approach — embracing constant change and adaptation — but once completed, it will stand as the best, enduring testament to innovation.”

B3X is an onchain derivatives protocol building the World Market for World Computer. Our vision is to utilize derivatives as go-to venue for onchain trading to faciliate launching of vaults, AI-driven tokenized funds, synthetic dollars (Ethena etc) and several other use-cases.

Vision

We believe that on-chain perpetual markets are more than just trading venues—they're modular, composable primitives in the broader DeFi ecosystem. While most treat perps as isolated platforms for speculation, we see them as foundational infrastructure for a new class of financial products. There’s significant untapped potential in building on top of these markets, and the team is focused on unlocking that opportunity—reimagining perps as DeFi Legos for innovation.

Community

B3X is a community-driven protocol.

We actively engage with your questions and welcome feedback that helps shape the future of the protocol.

Problems with Current Markets

There are several problems around perpetual futures onchain, a few of the key ones are:

DeFi's Never-Ending Cold Start Problem

Huge Liquidity Potential, Yet the Never-Ending Cold Start Problem

Crypto is now a $3.5T asset class, but we still face liquidity challenges and cold-start issues at perpetual futures market launches. With just 1% of the market cap ($35B), we should be able to create efficient on-chain perpetual future markets, yet we’re still struggling.

The problem is clear: Spot DEXes and lending markets have 10x the liquidity of derivatives. Why? Because we’re limiting perpetual futures to blue-chip assets and mainly USDC onchain. Even after more than 3 years of innovation, perpetual futures still lag behind other DeFi primitives.

By neglecting a wider range of assets, we’re missing huge liquidity potential and holding back the growth of on-chain derivatives. It’s time to rethink and expand these markets.

Discord
Twitter
Github
Website
DeFi's Never-Ending Cold Start Problem
Limited Utility for Existing Assets
CeFi Dominates with 100x Volume
Outdated DeFi Perps Offerings
Consistent Battle for Liquidity
Stablecoins with No Use-case
Unfair LP Treatment
No Settlement Venue is Best

Limited Utility for Existing Assets

Limited Utility for Existing Assets: A Persistent Nightmare for Holders

Sadly, the majority of assets have no utility beyond governance and staking yield. A fraction of them are allowed on lending protocols. For most, the only option is to hold and pray for an upside given their limited utility.

Holders often pray for some way these tokens can become useful, for their own sake, as they endure the PTSD of price actions — especially when every coin seems to be pumping except the ones they hold (which is often the sad truth). Perhaps if they could enjoy the price action of shiny new assets with their existing portfolio, they might just be able to endure the nightmare.

In the early days, we had Etherdelta — one of the first spot market CLOBs powered by ETH. Then came Poloniex, a once-popular centralized exchange dominated by BTC pairs. Later, BitMEX revolutionized the market with perpetual swaps powered by BTC.

Imagine the euphoria: you bought BTC, then used it to buy ETH. As ETH appreciated in BTC terms and BTC soared against USD, your returns multiplied. You could even use your BTC to long or short other assets, diversifying your portfolio.

Those days are long gone. Now, you can’t even long BTC with anything beyond blue-chip tokens or a few stablecoins at best. Even BTC — the asset with the highest market cap and largest holder base — has almost no utility in derivatives today.

If you lost USD in BTC-based perpetual futures position earlier, Bitcoin’s price appreciation could have helped recover some of your losses. However, with the majority of derivatives now collateralized by stablecoins, the opportunity for any upside recovery has been eliminated.

On-chain markets urgently need a transformative boost. To unlock their true potential, they must be powered by the most secure and highest Store of Value (SoV) asset, creating a foundation for robust, efficient, and inclusive global DeFi ecosystems. Once established, other assets will naturally follow, amplifying the ecosystem’s reach and impact.

Delta-Neutral Stablecoin

With World Market, protocols can launch their own stablecoins backed by derivative positions collateralized by their native tokens. This is similar to USDe by Ethena, but fully on-chain, decentralized, and capable of being collateralized by any on-chain asset.

Protocols can mint these stablecoins to bootstrap incentives, create DEX pools for liquidity both within and outside World Market, and avoid the sell pressure typically caused by directly allocating tokens for incentives.

Moreover, these stablecoins can be used to launch new markets in World Market, enhancing their utility beyond just being a stable asset or incentive.

Join the stablecoin revolution and leverage DeFi utilities offered by World Market for even more possibilities.

Architectural Design

The protocol’s architecture can be summarized as follows, where the components of the protocols are modular, hence the implementation of the such components relies on the actual implementation under proxy which are updated on regular basis. The possible key modules of the protocols are:

Chain: Manages protocol’s cross-chain messages, in order to achieve multichain modularity and enabling seamless trade execution for end-users.

Market: Manages protocol’s market-places, by allowing any users to permissionlessly create, modify or remove markets and adjust market related parameters.

Order: Accepts and handles protocol’s core functions, such as swaps & futures actions

Asset: Responsible for asset creation, management and adjustment asset related parameters

Oracle: Handles pricing logics and sources which includes off-chain and on-chain sources.

Role: Handles protocol’s roles which defines whitelisted actors for proper and secure functioning of the protocol.

Storage: Responsible for storing, updating and removing protocols storage state variables.

Keeper: Manages off-chain and on-chain keepers logics, their implementations and whitelisted keepers.

Router: Handles cross-contract communication for the protocol.

OrderBook: Responsible for storage and maintainence of orderbooks.

Solver: Handles intent-based solver system which lives fully onchain.

Building Solutions with Derivatives as a First Principle

Using derivatives as a first principle to address liquidity fragmentation and the usage crisis, we aim to balance markets by empowering end-users with modular tools — delta-neutral vaults, long/short one-vault strategies, stablecoin minting, and seamless utilization across applications, including the World Market.

We believe derivatives, particularly perpetual futures, have the potential to become world-class DeFi building blocks, paving the way for a new paradigm in DeFi markets.

Risk Management

LPs as First-Class Citizens: Mini DAOs

At World Market, LPs gain full control over the risk and economics of their markets, transforming them into first-class citizens of DeFi. This autonomy allows LPs to make decisions that align with their interests and contribute to the growth and evolution of their markets.

Protocols seeking to list themselves in existing markets will need to incentivize LPs to allocate capital to their market — usually a portion of open-interest capacity — through bribes or rewards.

LPs have the power to run their own governance, create customized incentives, and manage risks within their markets, maximizing their ownership and influence. This puts them in a unique position to shape the DeFi landscape, capturing more mindshare and market share compared to other protocols.

Introducing: The World Market

World Market as the trading engine of an entirely new market layer for the internet of value powered by on-chain assets.

B3X proposes a solution, the World Market — a global, permissionless blockchain marketplace that enables markets powered by any on-chain asset powered by perpetual futures.

For decades, markets have been a tale of exclusion, inefficiency, and centralized control. B3X envisions a new era — the World Market — a unified, decentralized solution to the failures of the past, inefficiencies of the present, and challenges of the future.

The World Market will simplify the market experience. Anyone can buy BTC using any memecoin, stablecoin, LP token, and more, all powered by derivatives. Too much risk? Take 1x leverage without the hassle of switching chains or selling your portfolio.

Why utilize derivatives for the World Market? Because we want everyone to access global markets without restrictions on what assets they can use. You should be able to trade, no matter how the markets move, using your favorite on-chain asset.

Using derivatives to power the World Market enables it to offer a vast range of market offerings, surpassing those of CeFi and current DeFi protocols, thereby creating a unique value proposition to onboard non-crypto natives and TradFi.

Through the World Market, B3X aims to enable deep liquidity to flow into derivatives, building efficient and effective capital markets. We are still in the early stages of derivatives, and the market potential is immense. For collateralization and deep liquidity, we have $3.5T worth of assets, while global derivatives represent a market worth over one quadrillion dollars.

We aim to onboard over 5% of the market capitalization to supercharge DeFi with the World Market. We know it’s a bold leap, but we’re not alone on this journey.

World Market transforms your portfolio into a capital-efficient powerhouse, empowering you to actively engage in DeFi rather than passively sitting on the sidelines, hoping for the upside. With World Market, you don’t just wait for the future — you trade it.

Consistent Battle for Liquidity

Collaborate, Don’t Compete: Building a Unified Global Liquidity Layer

DeFi must shift its mindset from competition to collaboration if we are to create a truly global liquidity layer that transcends blockchain ecosystems. The constant infighting over TVL and yield incentives only weakens the space, while CEXs have been pooling and sharing order book liquidity from day one, giving them a massive edge.

Vampire attacks and siloed liquidity fragment DeFi, making it harder to compete with CeFi’s scale and efficiency. By working together, DeFi protocols can unlock shared liquidity and scalability, paving the way for a seamless trading experience and sustainable growth for the entire ecosystem.

LPs as 1st Class Citizens

Reestablishing LPs as First-Class Citizens of DeFi.

It’s about rethinking the role of LPs, ensuring they aren’t just passive liquidity providers but active, well-rewarded participants driving the DeFi ecosystem forward.

LPs in the World Market have full governance over the market offerings provided by the pool. This ensures that LPs — who bear the majority of the risk — have a say in how their capital is allocated and utilized.

Imagine your positions as LPs on lending markets, other derivatives protocols, staking protocols, yield generating vaults — now available to be utilized as collateral to access World Market offerings — so you can long and short your next 100x gem without hassle.

World Market — can be powered by staked and restaking TVL enabling LPs to still become first-class citizen and furthermore do more with their LP positions — long or short — 100x memes, ai agents and yield across other protocols.

World Market will transform LPs into active traders, further fueling the growth of LPs and enhancing their influence within DeFi.

Not a trader, but looking for additional yield? Provide liquidity as LP at world market to get additional boosted yields on your existing LP position.

Yield-Bearing Stablecoin

World Market allows liquid staking assets that accrue yield to be utilized in the creation of yield-bearing stablecoins, similar to delta-neutral stablecoins. Thanks to the modular and composable design of World Market, we can introduce enhanced capital efficiency and utility to these assets.

These stablecoins will earn yield through the underlying asset and funding rates.

Like any other asset, these yield-bearing stablecoins can be leveraged to launch new markets on World Market, maximizing their utility and enabling even more opportunities for growth.

Boosting Token Utility

Most DeFi assets remain underutilized or entirely idle. But with the World Market, that’s a thing of the past. Now, your tokens can do more. In this new era, tokens are the new dollars.

Auto Deleverage

As one of the core risk management mechanics, ADL acts as a buffer to backstop profit distribution in an event of volatile price actions to prevent systematic risk to the market. If an asset is highly volatile, the protocol deploys additional measures such as ADL, to de-leverage the position automatically as the time passes if it occurs profits. In this mechanism, the pool which acts as counter-party to all the position in Open Interest forcefully takes over the position and liquidates it with profit to prevent future profit drainage. The priority queue depends on the nature of markets and the direction of trade. The ADL Keepers will consistently check the health of the active positions and deleverage by taking over the position and initiating force closure, which may result in partial liquidation.

Let us define PSP_SPS​, CPC_PCP​ as position size and collateral amount in USD and LPL_PLP​, as leverage of the position, then

LP=PSCPL_P = \frac{P_S}{C_P} LP​=CP​PS​​

Since PSP_SPS​ is a constant, hence the relation can be established as

LP∝1CPL_P \propto \frac{1}{C_P} LP​∝CP​1​

Funding Rate Collector

The Funding Rate Module makes funding rate arbitrage easy, so you don’t have to track it manually or manage complex positions.

Imagine continuously harvesting the funding rate — simply deposit into these vaults and let the yield come to you. Vault managers will actively allocate capital to delta-neutral positions with a negative funding rate. Once the rates turn positive, the positions are closed, and profits are realized.

With the development of the intent solver-based design, vault managers can seamlessly migrate positions from pool or CLOB to intent, often with opposite funding rate directions.

Thanks to the use of inverse perpetual futures, most markets on World Market allow positions to be delta-neutral, accruing negative funding rates without holding spot.

The goal is to make basis-point trading accessible to everyone and balance the open interest of World Market.

Each vault module will issue an LP token to represent your ownership, which can also be used to launch new markets on World Market.

Enabling Deep Liquidity

Rehypothecation: Empowering Liquidity, Preserving Ecosystems, Bridging Chains.

Rehypothecation allows us to use liquidity without emptying our partners and DeFi in general, instead onboard new liquidity on top of it.

If you’re a protocol with significant TVL that’s prone to idling and becoming stagnant, World Market can supercharge your protocol and enable your users to do more — without resorting to vampire attacks.

Such protocols can list trending DeFi assets, collateralized by their protocol tokens/assets and powered by World Market. This approach will not only boost their TVL but also generate additional yield while keeping users engaged.

World Market allows our competitors to tap into our deep liquidity, enabling them to scale themselves or build better markets using our robust infrastructure.

World Market will enable all protocols to access the markets beyond their own deployments.

World Modules

Modules: Our Modular Expansion for World Market Infrastructure

B3X is building not just the World Market but also pioneering use cases to unlock its full potential.

Introducing Modules — the infrastructure component that gives you the freedom to build anything with World Market. Whether it’s a synthetic dollar like Ethena’s, a Long-only Vault, a Short-only Vault, a Funding Rate Vault, or any other innovative solution, our modular design empowers you to create custom financial products that suit your needs.

The significance of Modules in World Market is straightforward: derivatives cater to the diverse use cases of general market participants. Some of them are as follows:

Human-driven Application Layer

This layer contains applications that require human oversight and decision-making. These components provide the interface through which users interact with the World Fund ecosystem.

Fund Marketplace

The Fund Marketplace connects investors with fund managers, enabling capital allocation and performance tracking:

  • Fund Discovery: Investors can browse and filter funds based on strategy type, performance metrics, risk profiles, and other key parameters

Long-Only Vault

With the World Market, you can create long-only vaults where the collateral staked in the vault is used to open long positions across specific markets as determined by the vault manager.

For example, you can create your own cryptocurrency index, like YOUR5, which tracks Asset A, B, C and D, with a equal weight distribution.

This module allows you to launch a vault that automatically takes long positions with 1x leverage and allocates capital according to the specified weights. Essentially, you’re trading your custom index in real-time.

Each vault module will issue an LP token to represent your ownership, which can also be used to launch new markets on World Market.

Unfair LP Treatment

LPs: Unfairly Treated as Passive, Second-Class Citizens

Liquidity providers (LPs) have long been treated as passive, second-class citizens in the DeFi ecosystem. Harmony is missing, and LPs often face chaos when supplying liquidity or taking actions, as market dynamics change constantly. LPs are left exposed to unpredictable risks without the tools to manage or capitalize on them effectively.

LPs should have the same rights as traders — able to actively manage and trade their positions. Since LPs essentially take the opposite side of trades, they must be empowered to hedge or even boldly trade using their LP positions.

Given the significant risks LPs face, they should be granted the power to govern where and how their capital is deployed. After all, LPs have been the financial backbone of DeFi, supporting innovation from its earliest stages. It’s time they are treated as the critical players they truly are.

Lending

The Lending Module extends World Market by enabling two key functions:

  • Traders can borrow against their positions.

  • LPs can borrow against their positions.

In return, lenders can capitalize on the positions and accrue yield — whether from funding rates on positions or fees on LP assets.

The goal of this module is to make World Market trades and LP positions more liquid, allowing for greater flexibility and yield generation across the ecosystem.

Future: Supercharged DeFi

World Market will enable users to speculate, hedge, or construct new financial primitives around previously untapped informational and economic domains.

On-chain perpetuals are set to change the game in DeFi, offering new ways to tap into liquidity, leverage, and financial innovation. With World Market, we’re taking it even further.

No Settlement Venue is Best

Redefining Market Efficiency: No Perfect Settlement, Only Better Solutions

Central Limit Order Books (CLOBs) aren’t the answer to efficient markets — they merely amplify stablecoin usage while sidelining other assets. Their structure prioritizes a narrow asset range, leaving the vast potential of DeFi in the dust.

On the other hand, liquidity pools aren’t perfect either. They require excessive inventory for trade execution, far more than other settlement systems, leading to inefficiencies and straining liquidity providers. While they can accommodate a wider range of collateral options, they fundamentally fall short in offering diverse market options.

Lastly, Intents only can handle markets which already exists for Solvers (Market Makers) to hedge, fundamentally restricting them to list anything not supported by CeFi, at current stage.

DeFi needs more than outdated paradigms — it requires innovative market structures that balance efficiency, inclusivity, and scalability to unlock its true potential. The current systems aren’t just imperfect — they’re limiting progress.

Perhaps we could focus on refining these designs and exploring ways to integrate them seamlessly for a more unified outcome.

Capital Allocation: Simple interface for investing in and withdrawing from funds

  • Performance Analytics: Comprehensive dashboards for tracking fund performance against benchmarks

  • Manager Profiles: Transparent information about fund managers, their track records, and strategy descriptions

  • Fund Builder

    The Fund Builder enables strategy creation through natural language, making sophisticated quantitative trading accessible to non-technical users:

    • Conversational Interface: Users describe trading strategies in plain language

    • LLM-Powered Translation: AI models translate natural language into executable trading code

    • Interactive Refinement: Users can iteratively improve strategies through feedback loops

    • Strategy Visualization: Clear visualization of strategy logic and expected behavior

    • Parameter Configuration: User-friendly interfaces for setting and testing strategy parameters

    Human-operated Funds

    Human-operated funds are managed directly by human fund managers who make strategic decisions while leveraging the platform's infrastructure:

    • Strategy Management: Tools for developing, backtesting, and deploying strategies

    • Portfolio Construction: Interfaces for building diversified portfolios across multiple assets

    • Risk Controls: Systems for setting and monitoring risk parameters

    • Execution Management: Tools for optimizing trade execution and monitoring market impact

    • Performance Reporting: Comprehensive analytics on fund performance and attribution

    Integration with AI Layer

    While human-driven, these applications seamlessly integrate with the AI-driven layer below:

    • Strategies created in the Fund Builder can be validated and optimized by the Quant Agent

    • Human-operated funds can leverage AI recommendations while maintaining human oversight

    • The Fund Marketplace incorporates AI-powered analytics to help investors make informed decisions

    This hybrid approach combines human creativity and judgment with AI-powered analytics and execution, creating a powerful synergy that amplifies the capabilities of both.

    User-Centric Intent, Action, and Execution Marketplace
    Yield Trading
    Simplified Market Experience
    LPs as First-Class Citizens: Mini DAOs
    Building Distribution for all — Chains, Protocols and Users
    Resolving Cold-start Problem
    Building Solutions with Derivatives as a First Principle
    Bootstrapping TVL Growth: Unlocking DeFi’s True Potential
    Boosting Token Utility
    Meaningful Second-order Incentives
    Boosting Economical Security of DeFi protocols
    Lending

    Funding Rate Collector

    Delta-Neutral Stablecoin
    Yield-Bearing Stablecoin
    Long-Only Vault
    Short-Only Vault
    Long vs Short Vault

    Launching New Markets

    With World Market, we are opening the door to a new era of on-chain markets, including but definitely not limited to:

    • LP Yields

    • Stablecoins

    • Bonds

    • Hashrate

    • Blobs

    LPs can fuel the growth of these markets with their own liquidity or incentivize existing LPs to expand their offerings.

    Traders simply choose their collateral and market offering to take positions seamlessly. The future of DeFi markets starts here.

    Bootstrapping TVL Growth: Unlocking DeFi’s True Potential

    The fundamental issue plaguing DeFi is the underutilization of existing TVL, resulting in low yields despite billions locked in protocols.

    World Market transforms this narrative, enabling full-scale utilization of TVL in ways previously unimaginable.

    With LPs elevated to first-class citizens, they can actively trade global markets using their LP positions, fostering excitement about DeFi’s future and their role in it. Beyond trading, new incentive programs amplify their engagement, paving the way for a more dynamic and sustainable ecosystem.

    This is how we redefine TVL growth — by unlocking untapped value.

    Meaningful Second-order Incentives

    Protocols can now issue stablecoins backed by their tokens, attracting users without creating downward pressure on their native assets. Through the World Market, they can build robust markets to maximize token utility and keep users actively engaged, no matter the market conditions.

    Simplified Market Experience

    World Market enables users to seamlessly achieve their intentions. For example, if a user wants to buy Asset A using Token B, but needs to supply Token C to acquire A, World Market automatically converts B to C and then purchases A — without the user even realizing it. Whether C is a token, LP, or any other asset, World Market takes care of the complexity, providing a frictionless experience for the user.

    Boosting Economical Security of DeFi protocols

    Increasing token utility reduces liquid supply, making tokens harder to acquire and governance attacks more difficult. For instance, in the COMP case, the reduced availability of tokens raises the threshold for creating proposals and achieving quorum, thereby enhancing governance security.

    Furthermore, protocols can empower stakeholders — such as stakers or holders utilizing tokens in other markets that boost value — to participate in governance. This reduces the influence of liquid token buyers who swoop in at the last moment to manipulate votes.

    Resolving Cold-start Problem

    DeFi has long struggled with liquidity issues, constantly hunting for deep liquidity and facing the same two questions: why you? and what do you offer? With World Market, liquidity finds its natural home, becoming capital efficient and no longer idly searching for utilization.

    World Market’s ability to launch new incentives and offer superior DeFi utility is what sets it apart.

    User-Centric Intent, Action, and Execution Marketplace

    World Market can act as the global execution marketplace where users can submit their intents, which will produce actions to achieve the intent and execute to get the result.

    From the previous example, imagine an AI agent processing the user’s intents (buy jitoSOL, sUSDe, and OM), which can be achieved through a series of actions (long jitoSOL, sUSDe, and OM), all executable on the World Market.

    Yield Trading

    Get exposure to yield without holding the underlying LP asset. LPs at World Market can list their yield, allowing traders and other market participants to easily trade it. We will be collaborating with yield trading protocols so you can leverage your LP tokens to hedge, short, or go long on your yield.

    With World Market, you can trade yields from Ethena, 10Y US Treasury, Aave’s WBTC yield, and much more.

    What’s even crazier? You can trade yield with yield to maximize your returns for even greater yield.

    Liquidity Pool Based Protocols

    Existing LP based perpetual futures DEXes have several limitations in enabling new markets to their existing offering. With World Market, they can easily scale up with their offering by launching Protocol-Owned Markets.

    Orderbook Based Protocols

    Existing Orderbook based protocols can use World Market to launch Protocol Owned Market catering towards their own community or users.

    Intent Based Protocols

    Intent based protocol often require additional solver or external solver. With World Market, they can launch markets available World Market Pool, Orderbook or Intent Solver where the settlement and liquidity is readily available for bootstrapping.

    Non-Derivative Protocols

    A existing LRT, LSD, DEX or any protocol with their own community can explore using World Market Interp Layer to enable perps as product offering without any additional efforts for additional source of revenue or market exposure.

    Unlimited Open Interest

    Efficient Liquidity, Unlimited Scale: The Future of Open Interest.

    The World Market adopts a pool-based design as the primary settlement venue in its first iteration, leveraging its flexibility for diverse market offerings and collateralization.

    However, it is different than the existing pool-based models.

    In each World Market pool, liquidity moves with the market offering demands in real time. Because market offerings will usually higher than majority of the protocols, liquidity is dynamically allocated yet readily available.

    For example, if a World Market pool has 500 market offerings and a total liquidity of 100M, it does not necessarily mean that the 100M is evenly split across the 500 markets. Instead, the entire 100M is initially available to each of the 500 market offerings. This creates a dynamic competition to utilize the liquidity, effectively eliminating idle liquidity and ensuring it is directed toward use cases that can employ it most efficiently.

    To enable true price discovery and a familiar UX, we will be working on building a fully on-chain orderbook to scale the World Market’s liquidity. Later, we will introduce intent-based settlement to allow LPs and traders to hedge effectively and accelerate the World Market.

    Orders will be routed to best trade execution venue price-cost priority.

    Furthermore, the pool-based venue acting as the counterparty for the first iteration of World Market will leverage an orderbook to hedge itself. Additionally, market makers (MMs) or traders in the orderbook can use the intent-based model to hedge further, and vice versa. This ensures that liquidity is efficiently utilized across all models, enabling us to scale to a virtually unlimited open interest model. These venues — pool, orderbook, and intent — can tap into an Insurance Fund to borrow capital for hedging and covering costs.

    This will enable the Pool-model design can support deeper liquidity than existing protocols, and make the World Market more capital efficient.

    Our main goal is to make World Market accessible to all end users irrespective of the chain they are on.

    Solving the Crypto UX Nightmare

    The Average Crypto User: A Tale of 100x Gains and a Maze to Navigate

    Imagine you’ve already invested in ai16z and made your 100x return. Now, you want to diversify into jitoSOL on Solana, sUSDe on Ethereum, and OM on Mantra for stable yields and exposure to Solana’s price action and RWA chains.

    The current process would involve selling ai16z, using part of it to buy jitoSOL, then bridging some to Ethereum to swap for sUSDe or stake it. You’d then swap to sUSDe, and finally, bridge the rest to Mantra to buy OM or stay on Ethereum to purchase OM there.

    This is a terrible user experience. Most users will struggle with this complexity. We’re not there yet, even with AI agents. Users must navigate through three fundamentally different blockchains (Solana, EVM, Cosmos), which is overwhelming.

    The World Market is here to eliminate this UX nightmare and onboard average users without the need for endless blockchain education.

    With the World Market, you can directly use ai16z tokens to buy jitoSOL, sUSDe, and OM — no need for selling, bridging, or chain-hopping. Enjoy the same upside and yield while maintaining the full potential of your ai16z tokens.

    Through the World Market, users can now:

    • Trade any asset or data stream, literally.

    • Trade using the majority of on-chain assets, for real.

    What can you trade on?

    Cryptocurrency, forex, commodities, stocks, indices, etfs, hashrates, gas prices, bonds, yields, funds, predictions, trends, culture, memes, gdp growth, time assets, birth rates, median income, stablecoins, real estate, and so much more.

    World Market presents infinite possibilties.

    What can you trade with?

    Almost any onchain asset including:

    • native assets (BTC, ETH, SUPRA, etc),

    • liquid staking assets (wstETH, rETH, LBTC, etc),

    • liquid restaking assets (eETH etc),

    • RWA assets (BENJI, BUIDL, etc),

    Your portfolio holds more value than you think — capitalize its true potential with the World Market.

    Building Distribution for all — Chains, Protocols and Users

    World Market is engineered to seamlessly integrate with every protocol, blockchain, and end-user, creating a universal distribution layer.

    Chains

    World Market transforms how liquidity operates across blockchains by providing a unified market of markets. As more markets and chains integrate with World Market, each deployment benefits from broader access to liquidity, without the need to extract TVL or yield from one another.

    Instead of draining value, World Market strengthens TVL across chains, enhancing the ability for users to unlock new opportunities with their holdings, while preserving and growing their assets.

    World Market isn’t just about blockchains — it connects directly with protocols and their users, offering a wide array of use cases to the blockchain ecosystem they can:

    • Generate additional yield with existing TVL

    • Onboard capital-efficient TVL without draining it

    • Access deep liquidity without vampire attacking other chains

    • Enable DeFi-native utilities for ecosystem projects and assets

    Protocols

    With World Market, protocols can take control and launch their own markets, empowering their users with unparalleled opportunities:

    • Launch your own stablecoin using our customizable modules

    • Create your own market on World Market, enabling users to long or short your token

    • Collateralize a market with your token, allowing holders to long and short the world using your asset

    • Offer long-only vaults for your token holders

    Users

    At World Market, users are more than just traders — they’re power users, capable of:

    • Trading with portfolio assets without the need to sell

    • Generating additional yield with existing holdings

    • Creating custom indices and personalized trading strategies

    • Building and managing trading vaults

    And much more, all at your fingertips.

    Pricing Mechanism

    Pricing is one of the most critical components of any derivative protocol. To achieve our vision, we have implemented additional measures to ensure fair, transparent and tamper-proof pricing for all the end-users irrespective of role: Liquidity Provider or Traders.

    The protocol adapts intent-based design to compute, validate and submit prices on-chain for intent execution. Upon user's request submission to the smart contract, a series of on-chain and off-chain events occur to submit the pricing required for executing the request.

    General Pricing Formula

    The final price ‘ PfP_{f} Pf​’ of an asset at time ‘t’ on the protocol can be represented as

    Pf=Φ∗[γPc+δPdγ+δ]P_{f} = \Phi * \left[ \frac{\gamma P_{c} + \delta P_{d}}{\gamma + \delta} \right]Pf​=Φ∗[γ+δγPc​+δPd​​]

    where PdP_{d}Pd​ can be defined as the price of the asset from decentralized sources, represents the respective pricing and weight of the decentralized sources while is a black box function to ensure tamper-proof pseudo-deterministic price for fair trade execution,

    and can be defined as the price of the asset from real-world sources and represents the respective pricing and weight of the real-world sources in form of a time-series function as

    For simulation, we will plug in and define then

    where

    Liquidation Price

    The liquidation price for an asset for all active positions will differ, but considering rest of the parameters constant, it can be defined as

    The liquidation price of the position is not computed as general pricing formula to ensure fair and transparent liquidation, especially in the event of volatile market conditions.

    Hence, at any given time ,

    Spread Factor

    Based on the volatility of the market and asset, the protocol deploys additional parameters to safeguard LPs and prevent systematic risk to the protocol. One such factor is Spread Factor. If Spread Factor, is defined for an asset in a market by market creator, the final price to open/execute a trade in any direction will be

    Depending on direction,

    And the final price to close such positions can be defined as

    Depending on direction,

    Architecture

    World Fund features a layered, modular architecture designed for flexibility, scalability, and seamless integration with existing DeFi infrastructure. The system is structured into four distinct layers that work in concert to deliver a comprehensive fund management ecosystem.

    Architecture Overview

    The World Fund architecture consists of four primary layers:

    1. - The interface for traders, investors, and fund managers

    2. - Applications requiring human oversight and decision-making

    3. - Autonomous components that operate with minimal human intervention

    4. - Foundation services and tools supporting the entire ecosystem

    Each layer is designed with clear responsibilities and interfaces, creating a modular system that can evolve over time.

    Decoupled Market Integration

    A key architectural advantage of World Fund is its purpose-built integration with World Market, our specialized Perpetual DEX. This synergistic design provides unique benefits:

    • Optimized performance through deep integration between strategy execution and market infrastructure

    • Enhanced feature compatibility with specialized World Market capabilities designed specifically for World Fund strategies

    • Superior security through end-to-end control of the trading lifecycle

    • Streamlined user experience with unified account management and permissions

    By designing World Fund and World Market in tandem, we've been able to create specialized market mechanisms that enhance strategy execution beyond what would be possible with generic third-party integrations.

    Secure Transaction Execution

    World Fund utilizes an innovative Agent Wallet mechanism to ensure secure and automated strategy execution on World Market. This security-focused approach works through limited-permission secondary wallets that:

    • Execute trades and manage positions without withdrawal permissions

    • Apply strategy-specific risk parameters defined by the fund creator

    • Operate within strictly defined boundaries and fail-safes

    This approach ensures both autonomy and security in strategy execution while maintaining complete separation between fund custody and operational execution.

    Each architectural layer is described in more detail in the following sections.

    Decentralized Architecture

    World Fund is built on a fully decentralized architecture that ensures transparency, security, and resilience. This architecture enables trustless operation while maintaining high performance and adaptability.

    Decentralized Governance

    The World Fund ecosystem is governed through decentralized mechanisms:

    • Protocol Governance: Key protocol parameters and upgrades are determined through on-chain voting

    • Strategy Governance: Validation and deployment of strategies to the curated library follows a decentralized approval process

    • Risk Parameter Governance: Risk controls and limits are subject to decentralized oversight

    • Fee Structure Governance: Economic parameters are adjusted through community governance

    On-chain Strategy Execution

    Strategies are executed through a transparent on-chain process:

    • Immutable Strategy Storage: Validated strategies are stored on-chain with tamper-proof guarantees

    • Transparent Execution: All strategy execution steps are visible and verifiable on-chain

    • Verifiable Performance: Strategy performance metrics are calculated from on-chain data

    • Automated Settlements: Position adjustments and fund allocations occur through smart contracts

    Off-chain Computation with On-chain Verification

    To optimize for both performance and trust, World Fund employs a hybrid approach:

    • Off-chain Computation: Intensive calculations for strategy generation and optimization occur off-chain

    • Off-chain Data Processing: Market data analysis and signal generation happen off-chain for efficiency

    • On-chain Verification: Key results and decisions are verified and recorded on-chain

    • Cryptographic Proofs: Where appropriate, zero-knowledge proofs verify off-chain computations

    Security Model

    The decentralized architecture incorporates multiple security layers:

    • Multi-signature Controls: Critical actions require approval from multiple authorized parties

    • Time-locks: Important system changes include time-delay mechanisms for safety

    • Circuit Breakers: Automatic safeguards halt operations under extreme conditions

    • Formal Verification: Core smart contracts undergo formal mathematical verification

    Agent Wallet System

    A key innovation in World Fund's decentralized architecture is the Agent Wallet system:

    • Limited-Permission Execution: Agent Wallets can only perform specific trading actions, with no withdrawal capabilities

    • Strategy-Specific Parameters: Each wallet operates within clearly defined boundaries set by the strategy creator

    • Cryptographic Authentication: Secure authentication ensures only authorized systems can initiate actions

    • Transparent Operations: All Agent Wallet actions are publicly visible and auditable

    Cross-chain Compatibility

    The architecture supports operation across multiple blockchain ecosystems:

    • Chain-Specific Adapters: Integration with multiple blockchain environments

    • Uniform Strategy Interface: Consistent strategy representation regardless of underlying chain

    • Cross-chain Synchronization: Coordination of strategy execution across different chains

    • Liquidity Bridges: Seamless movement of capital between different blockchain environments

    This comprehensive decentralized architecture ensures that World Fund combines the benefits of trustless operation with the performance and sophistication required for advanced fund management.

    Long vs Short Vault

    The Long vs Short Vault Module lets users take both long and short positions simultaneously, depending on their strategy. Collateral deposited into the vault is used to create positions on World Market that align with the vault’s intended strategy.

    For example, if you’re a SOL maxi and ETH skeptic, you can long SOL while shorting ETH at the same time, effectively creating a SOL/ETH pair. If SOL’s price rises or ETH’s price falls, you’ll profit.

    This module empowers users to create dominance pairs, exotic pairs, and many more customized positions, enhancing flexibility and trading opportunities.

    Core Components

    World Fund's functionality is delivered through three core components that work together to enable sophisticated fund creation, validation, and execution. Each component is designed to solve specific challenges in the fund management process.

    These components form the technological foundation of World Fund, working in concert to create a comprehensive fund management platform.

    Fund Builder

    The Fund Builder component enables the creation of trading strategies through natural language, making sophisticated quantitative trading accessible to non-technical users. Through an intuitive conversational interface, users can describe their trading ideas in plain language and have them transformed into executable code.

    Quant Agent

    The Quant Agent is the central intelligence engine that generates, tests, and optimizes trading strategies. Using rigorous scientific methodologies, it systematically prevents overfitting while ensuring strategies are robust across different market conditions. The Quant Agent leverages the Model Context Protocol (MCP) to access specialized tools and capabilities.

    Strategy Framework

    The Strategy Framework provides the structure for creating, validating, and executing trading strategies. It includes the Strategy Factory and Strategy Selector (SFSS) system that ensures strategies meet rigorous standards before deployment, and supports a decoupled execution architecture that separates signal generation from order execution.

    Together, these components create a comprehensive ecosystem for fund management that combines the accessibility of natural language interfaces, the rigor of scientific validation, and the efficiency of automated execution.

    First-Principle Orderbook Design

    CLOBs for building World Market Pricing Engine

    Traditional CLOBs

    World Market CLOBs: Introducing DMM

    Introducing the DMM Module — Designated Market Maker Vault Module. Collateralized by any on-chain asset, not just stablecoins, it enables the trading of Asset-Margined Perps. LPs supply assets, while DMMs implement market-making strategies to create order books and take performance fees. LPs have the power to vote on which markets to list, ensuring true governance while DMMs offer feedback and perform risk management.

    For example: With World Market, we can create our own CLOB markets for futures, powered by BTC — reminiscent of BitMEX’s pioneering approach. Additionally, launching BTC-powered spot CLOB markets powered by World Market can accelerate the growth of BTCFi.

    Conclusion

    World Fund represents a paradigm shift in how investment funds are created, managed, and accessed within the DeFi ecosystem. By leveraging cutting-edge artificial intelligence and a modular architecture, we have addressed the fundamental challenges that have limited the potential of decentralized fund management.

    Key Innovations

    Through our integrated platform, we have democratized access to sophisticated quantitative trading strategies that were previously available only to elite institutions:

    • Natural Language Strategy Creation: Making fund creation accessible to anyone, regardless of technical background

    • Intelligent Quant Agent: Combining rigorous scientific methods with an open architecture enabled by the Model Context Protocol (MCP)

    • Decoupled Execution Architecture: Separating Signal Generators (for signal production) from Trader Agents (for execution optimization)

    • Integration with World Market: Purpose-built synergy with our specialized Perpetual DEX for maximum performance and security

    Addressing Core Challenges

    World Fund directly addresses the key challenges faced by decentralized fund management:

    • Reducing Technical Complexity: Enabling fund creation through natural language, removing technical barriers

    • Preventing Strategy Overfitting: Implementing rigorous validation methodologies to ensure strategy robustness

    • Enabling Dynamic Adaptation: Creating systems that can detect market regime changes and adapt accordingly

    • Powering Autonomous Operations: Delivering end-to-end AI-powered fund management from strategy creation to execution

    The Path Forward

    As World Fund evolves, we envision an ecosystem where:

    • Quantitative trading strategies become accessible to everyone, not just specialized institutions

    • The quality of trading strategies improves through rigorous scientific validation

    • Market efficiency increases as sophisticated strategies become more widely deployed

    • Capital allocation becomes more meritocratic based on genuine strategy performance

    Our Vision

    Ultimately, World Fund aims to create a more equitable financial ecosystem where:

    • Access to sophisticated trading tools is determined by ideas, not institutional affiliation

    • Strategy performance is the result of genuine insight, not data mining and overfitting

    • AI works alongside humans to enhance creativity and execution efficiency

    • The boundaries between traditional and decentralized finance continue to blur

    By combining the best elements of artificial intelligence, quantitative finance, and blockchain technology, World Fund stands at the forefront of the next evolution in decentralized finance—creating a more accessible, efficient, and innovative investment landscape for all participants.

    Stablecoins with No Use-case

    Stablecoins Everywhere, But Where Are the Markets to Use Them?

    The crypto space is flooded with stablecoins, yet they offer little beyond holding value. Even as a holder, what can you actually do with them? Can you buy crypto directly? No, they’re often swapped into USDC or ETH or SOL first. Can you use them seamlessly in order books? Absolutely not — USDC dominates there too. Are there meaningful utilities elsewhere? Perhaps, but they remain limited.

    Stablecoins promised to revolutionize DeFi, yet their utility remains painfully narrow. It’s time to rethink how stablecoins integrate with broader markets and unlock their true potential beyond just sitting idle or being intermediaries in swaps. DeFi deserves better.

    AI-driven Application Layer

    The AI layer houses autonomous components that operate with minimal human intervention, forming the intelligent core of the World Fund ecosystem.

    Quant Agent

    The Quant Agent is the central intelligence engine that generates, tests, and optimizes trading strategies through an iterative process:

    • Strategy Generation: Creates trading strategies based on both historical patterns and financial principles

    Fees

    Fee structure for sustainable yield and trades

    Futures Market Fees

    The Futures Market has following fees to incentivise LPs and traders:

    • Opening and Closing Fees

    Our Call to Action

    On-chain perpetual markets are more than isolated trading venues — they are the foundational DeFi Legos for building the next wave of innovative financial products. This untapped potential is an open invitation to pioneers ready to redefine composability and unlock opportunities that no one has explored yet.

    We are building the World Market to unlock this the new era of DeFi.

    Why is World Market so important?

    If you believe that

    • The use case of decentralized finance is permissionless global markets.

    • The addressable market for global liquidity is boundless in DeFi.

    References

    This document draws on a wide range of research and foundational work in quantitative finance, artificial intelligence, and decentralized systems. The following references provide additional context and background for the concepts presented in this litepaper.

    Quantitative Finance

    • Bailey, D. H., Borwein, J. M., López de Prado, M., & Zhu, Q. J. (2014). Pseudo-Mathematics and Financial Charlatanism: The Effects of Backtest Overfitting on Out-of-Sample Performance. Notices of the American Mathematical Society, 61(5), 458-471.

    Liquidation

    The protocol allows following types of liquidation to prevent systematic risk:

    • Partial Liquidation

    • Full Liquidation

    Partial Liquidation

    Asset Management

    Any market requires one or more assets to be whitelisted for its successful creation. A non-whitelisted asset cannot be used for market creation. The protocol uses a two-step process to reduce the protocol’s security and systematic risk. All the logical implementation of handling asset-related parameters is stored in the Asset Manager. All asset-related parameters are available to be configured at the time when the user requests whitelisting of an asset by calling requestAddAsset(), which takes several asset-related parameters. Upon receipt of such request, the protocol validates the request and handles the addition of the assets based on risk parameters.

    Some of the key parameters for an asset, for example, ETH requested to be whitelisted are:

    Shortable: Allow anyone to short ETH.

    Longable: Allow anyone to long ETH.

    Stable: Allow anyone to use ETH as a stablecoin asset in the protocol.

    Longable: Allow anyone to long ETH.: Allow anyone to use ETH as a collateral for trading.

    Reference: Allow anyone to use ETH as a reference asset.

    Risk Factors

    Several attack vectors have been mitigated for the long-term sustainability of the protocol across different core components, which can be summarized as:

    Front-running

    As one of the oldest and still most common attack vectors for DeFi in general, front-running has been mitigated by using a two-step process for all actions corresponding to the user’s intent. For any user’s intent, there will be a request, then validation, and finally, there will be a response in the form of rejection or execution.

    Front-running, a persistent threat in Decentralized Finance, has been effectively addressed through the adoption of a two-step process for all user actions. This approach ensures that each user's intent undergoes a thorough validation process, starting with a request and resulting in a response of either rejection or execution of the action.

    The protocol implements a two-step process for all user actions where each user’s intent undergoes an adaptive validation process

    The Problem

    Despite the rapid growth of DeFi, the creation and management of investment funds within this ecosystem face significant challenges that limit innovation, accessibility, and performance. World Fund addresses four critical problems that currently hinder the development of sophisticated fund management in decentralized finance.

    Technical Complexity in Fund Creation and Management

    Developing and managing investment funds in DeFi requires extensive technical expertise across multiple domains:

    • Smart contract development skills for creating fund structures and executing trades

    Settlement Design

    The settlement design has been briefly explained in the section below:

    Allow ecosystem projects to hedge their treasury efficiently
  • Launch incentive-based stablecoins for ecosystem growth

  • And so much more, fueling DeFi’s evolution and scalability.

  • Generate more yield for stakers through innovative solutions

  • Earn additional yield for your treasury by participating as a World Market LP

  • And much more, pushing the boundaries of DeFi innovation.

  • Hedging LP positions or generating more yield

  • Trading LP positions or with LP tokens

  • Going long or short on the world’s markets

  • Engaging in basis-point trading strategies

  • Trading seamlessly without the need for bridging or switching chains

  • Security Audits: Regular third-party security audits of all components

    Innovation accelerates through the open architecture enabled by the Model Context Protocol

    Rigorous Validation: Employs advanced techniques to prevent overfitting and ensure strategy robustness

  • Adaptive Optimization: Continuously refines strategies based on changing market conditions

  • Multi-model Approach: Leverages multiple AI models to analyze different aspects of market behavior

  • MCP Integration: Extends capabilities through the Model Context Protocol to access specialized tools

  • The Quant Agent systematically addresses Bailey's paradox: "The more we optimize strategy performance to the available data, the less we can rely on the backtest as an indicator of future performance."

    AI-operated Funds

    AI-operated funds execute strategies autonomously, managing capital based on carefully validated approaches:

    • Autonomous Operation: Funds run with minimal human intervention based on predefined strategies

    • Risk-aware Execution: AI continuously monitors and adjusts positions based on risk parameters

    • Regime Detection: Systems automatically identify market regime changes and adapt accordingly

    • Multi-strategy Deployment: Single funds can operate multiple uncorrelated strategies simultaneously

    • Transparent Reporting: Despite autonomous operation, all actions are fully auditable and explained

    Trader AI Agent

    The Trader AI Agent focuses exclusively on optimizing trade execution based on strategic directives:

    • Execution Optimization: Minimizes slippage and market impact through intelligent order routing

    • Adaptive Timing: Adjusts execution timing based on market conditions and volatility

    • Multi-venue Execution: Can execute across different liquidity pools for optimal pricing

    • Cost Analysis: Continuously analyzes and reports on transaction costs and execution quality

    • Order Type Selection: Intelligently selects between market, limit, and advanced order types

    Intelligence Architecture

    The AI components are built on a sophisticated intelligence architecture:

    • Ensemble Methods: Multiple models working in concert to improve decision quality

    • Explainable AI: All decisions can be traced and explained, avoiding "black box" approaches

    • Reinforcement Learning: Systems improve over time based on execution results

    • Transfer Learning: Knowledge from one market or asset class can be applied to others

    • Anomaly Detection: Continuous monitoring for unusual market conditions or system behavior

    This layered AI approach creates a robust system where each component specializes in a specific aspect of the fund management process, while maintaining clear separation between strategy generation, signal processing, and order execution.

    The killer usecase of DeFi is creating markets that have the power to transform the world.

    Why now?

    This is because:

    • Many high-performance chains are pushing the theoretical limits of transactions per second with ultra-low latency block times.

    • These chains offer gigagas capacity, enabling complex computations without running out of gas.

    • Blockchain-level automation is now possible, powering high-performance systems with ease.

    • Low-latency, high-performance oracles operate entirely on-chain, ensuring seamless utilization.

    • AI-Agentic future enables better interoperability, enhanced risk management, and on-time execution, all with high efficiency.

    • All of this is achieved at a fraction of the cost compared to past blockchain systems.

    We believe with such developments and many more to come, DeFi markets can start going head to head with CEX’s on performance and scale to support TradFi volumes down the line.

    World Market is not just a vision, its a call to action for all.

    SwapEnabled: Allow anyone to swap for or to ETH.

    LeverageTradingEnabled: Allow anyone to open ETH trades. Works only if Reference, Shortable and Longable are true for ETH.

    DecentralizedSourcesEnabled: Allow ETH to have decentralized pricing source such as Chainlink, Pyth etc. for price discovery.

    CentralizedSourcesEnabled: Allow ETH to have real world pricing sources such as Binance, Bybit, etc for price

    For each asset, the Asset Manager will create an object of type CryptoAssetProps or TimedMarketAssetProps after performing mandatory checks actions both on-chain and off-chain, such as validating price feeds, chainids of the addresses and asset parameters. Upon passing all the valid checks, the asset will be whitelisted in the protocol to be used as a market asset.

    As decentralized finance continuous to grow, we will see influx of unique assets emerging which can also be whitelisted in the protocol to create a market.

    Sequencer Down or Blockchain Congestion

    While this is not common, the on-chain contracts and off-chain infrastructure are purposefully designed to handle the cases where such events occur allowing for the operation of the protocol to adapt as needed.

    Once the blocks are being produced, the prices in the pendingQueue will be reviewed and validated before any existing or previous orders are executed by the Execution Engine.

    Malicious Assets or Markets Parameters

    If a bad actor requests asset whitelisting, creation of a market, modification of a market, or other asset/market related parameters, the Asset Manager will handle proper validation before any request is passed onto the Execution Engine. The Execution Engine will run its own validation checks to ensure that no malicious actions disguised as requests are executed. In the early stages of the protocol, several additional internal checks will be followed until the protocol is handed over to the DAO for decision-making.

    Maximum and Oracle Extractable Value

    Several validation logics have been implemented on the on-chain and off-chain infrastructure to ensure maximum possible security. As previously shared, our two-step process reduces the chances of MEV and OEV attacks to almost zero.

  • Quantitative finance knowledge for designing effective trading strategies

  • Data science capabilities for analyzing market data and performance metrics

  • Blockchain infrastructure understanding for efficient on-chain operations

  • This high technical barrier prevents many talented fund managers from participating in the DeFi ecosystem, limiting the diversity and innovation of available investment options.

    Strategy Overfitting and Validation Challenges

    Trading strategies often perform well on historical data but fail in live markets due to overfitting:

    • Conventional backtesting methods frequently produce misleading results

    • Limited tools exist for rigorous out-of-sample validation in DeFi environments

    • Few platforms offer systematic approaches to strategy validation across different market regimes

    This leads to strategies that appear promising during development but underperform when deployed with real capital.

    Lack of Dynamic Strategy Adaptation

    Cryptocurrency markets are characterized by rapidly changing conditions and regime shifts:

    • Most trading strategies are optimized for specific market conditions

    • Manual intervention is typically required to adjust strategies, creating operational friction

    • Few solutions exist for automatically detecting market regime changes and adapting accordingly

    Limited Autonomous AI-Powered Fund Operations

    While AI has transformed many industries, its application in autonomous fund management remains underdeveloped in DeFi:

    • Current AI implementations in trading are often limited to signal generation rather than end-to-end fund management

    • Existing solutions lack the ability to autonomously execute complex strategies while managing risk

    • Integration between AI systems and on-chain execution remains fragmented

    World Fund's architecture directly addresses these challenges through its integrated approach to fund creation, validation, adaptation, and autonomous operation. Discover how in our Architecture Overview and Core Components sections.

    nnn
    Pi,WiP_{i}, W_{i}Pi​,Wi​
    Φ\PhiΦ
    Pd=∑i=1i=nPiWiWi=P1W1+P2W2+...+PnWnW1+W2+...+WnP_{d} = \sum_{i=1}^{i=n} {\frac{P_{i}W_{i}}{W_{i}}} = {\frac{P_{1}W_{1}+P_{2}W_{2}+...+P_{n}W_{n}}{W_{1}+W_{2}+...+W_{n}}}Pd​=i=1∑i=n​Wi​Pi​Wi​​=W1​+W2​+...+Wn​P1​W1​+P2​W2​+...+Pn​Wn​​
    PcP_{c}Pc​
    mmm
    Pj,WjP_{j},W_{j}Pj​,Wj​
    Pc=∑i=0i=nCiPt−i=C0Pt+C1Pt−1+...+CnPt−nP_{c} = \sum_{i=0}^{i=n} C_{i}P_{t-i} = C_{0}P_{t} + C_{1}P_{t-1} +...+ C_{n}P_{t-n}Pc​=i=0∑i=n​Ci​Pt−i​=C0​Pt​+C1​Pt−1​+...+Cn​Pt−n​
    i=2i=2i=2
    C0=0.80,C1=0.15,C2=0.05C_{0} = 0.80, C_{1}=0.15, C_{2}=0.05C0​=0.80,C1​=0.15,C2​=0.05
    Pc=0.80Pt+0.15Pt−1+0.05Pt−2P_{c} = 0.80P_{t} + 0.15P_{t-1} + 0.05P_{t-2}Pc​=0.80Pt​+0.15Pt−1​+0.05Pt−2​
    Pt=∑j=1j=mPjWjWj=P1W1+P2W2+...+PmWmW1+W2+...+WmP_{t} = \sum_{j=1}^{j=m} {\frac{P_{j}W_{j}}{W_{j}}} = {\frac{P_{1}W_{1}+P_{2}W_{2}+...+P_{m}W_{m}}{W_{1}+W_{2}+...+W_{m}}}Pt​=j=1∑j=m​Wj​Pj​Wj​​=W1​+W2​+...+Wm​P1​W1​+P2​W2​+...+Pm​Wm​​
    PL=PTWAPW1+PVWAPW2W1+W2P_{L} = \frac{P_{TWAP}W_{1}+P_{VWAP}W_{2}}{W_{1}+W_{2}}PL​=W1​+W2​PTWAP​W1​+PVWAP​W2​​
    ttt
    PL≠PfP_{L} \ne P_{f}PL​=Pf​
    SfS_{f}Sf​
    Popen=Pf±SfP_{open} = P_{f} \pm S_{f}Popen​=Pf​±Sf​
    PL=Pf+Sf,PS=Pf−SfP_{L} = P_{f} + S_{f} , P_{S} = P_{f} - S_{f} PL​=Pf​+Sf​,PS​=Pf​−Sf​
    Pclose=Pf∓SfP_{close} = P_{f} \mp S_{f}Pclose​=Pf​∓Sf​
    PL=Pf−Sf,PS=Pf+SfP_{L} = P_{f} - S_{f} , P_{S} = P_{f} + S_{f} PL​=Pf​−Sf​,PS​=Pf​+Sf​
    Learn more about Fund Builder
    Learn more about Quant Agent
    Learn more about Strategy Framework
    Unlimited Open Interest

    Future-proofing through coordinated development roadmaps between both platforms

    User Layer
    Human-driven Application Layer
    AI-driven Application Layer
    Infrastructure Layer
    World Fund Architecture
    Borrowing Fees
  • Skew-based Funding Fees

  • Fixed Opening and Closing Fees

    When traders open a trade on the protocol, an opening fee is deducted from the collateral to facilitate execution of the trade. Similarly, a closing fee is deducted from the collateral when the traders close their positions.

    The opening and closing fees are fixed and depend on the market creator. Hence, each market may have different fees.

    Dynamic Borrowing Fees

    The market pool acts as a counterparty in an event of market skew. Hence, all positions pay a borrowing fee on hourly basis for sustainable operation of the protocol in event of skew. In case, there is no skew and very low Open Interest, borrowing fees tend to be 0.

    Let nnn be the total time interval in hours until which the position was opened for, then borrowing fees of the position, fbf_{b}fb​ at any time ttt can be defined as

    and we can define f(t)f(t) f(t) as

    where ROI(t)R_{OI} (t)ROI​(t) is the reserve amount in USD for all opened positions at time ttt, RTR_{T}RT​ is the total reserve amount in USD for the market, FmaxF_{max}Fmax​ is the maximum allowed borrowing fees for the market defined and SSS is the position size.

    Since FmaxF_{max}Fmax​,RTR_{T}RT​, SSS are constant throughout the position time, so

    hence, we can say as the open interest of the market increase the borrowing fees increase and vice versa.

    Skew-based Funding Fees

    Let the Active Open Interest Skew be θ\theta θ, then

    where LLL is the sum of open interest on Long side, SSS be the sum of open interest on short side and OOO be the sum of total open interest in USD.

    If RusdR_{usd}Rusd​ represents pool's maximum reserve amount available for an asset, then

    Then the funding fee of a position can be defined as

    where Λ\LambdaΛ is the asset's funding constant and λ\lambdaλ is the asset's funding power constant.

    Direction of Funding Fees

    The possible output of the function is 111 which means long will pay short and −1-1−1 means shorts will pay long.

    fb=∫0nf(t)where0<t≤nf_{b} = \int_{0}^{n} f(t) \quad where\quad0<t\leq n fb​=∫0n​f(t)where0<t≤n
    f(t)=rOI(t)RT  ×Fmax  ×Sf(t) = \frac{r_{OI}(t)}{R_{T}} \; \times F_{max} \;\times Sf(t)=RT​rOI​(t)​×Fmax​×S
    f(t)=κ  ∗rOI(t)f(t) = \kappa \;* r_{OI}(t)f(t)=κ∗rOI​(t)
    κ=FmaxSRT \kappa = \frac{F_{max}S}{R_{T}} κ=RT​Fmax​S​
    fb∝rOIf_{b} \propto r_{OI}fb​∝rOI​
    θ=∣L−S∣O\theta = \frac{|L - S|}{O} θ=O∣L−S∣​
    ϑ=∣L−S∣Rusd\vartheta = \frac{|L - S|}{R_{usd}} ϑ=Rusd​∣L−S∣​
    F=Λ∗θλOF = \frac{ \Lambda * \theta^{\lambda}}{O} F=OΛ∗θλ​
    Direction=L−S∣L−S∣Direction = \frac{L-S}{|L-S|}Direction=∣L−S∣L−S​
    stablecoins (cdxUSD, lvlUSD, USDe,, USDM, DAI, FUSD, USD0, USDS, USDX etc),
  • LPs assets (Aave staked asset, Pendle’s PT, GLP, GM, gDAI, etc) as well as B3X's World Market LP token,

  • MEMEs (MEME, PEPE, SHIB, etc)

  • and much more.

  • López de Prado, M. (2018). Advances in Financial Machine Learning. Wiley.

  • Aronson, D. (2006). Evidence-Based Technical Analysis: Applying the Scientific Method and Statistical Inference to Trading Signals. Wiley.

  • Kakushadze, Z., & Serur, J. A. (2018). 151 Trading Strategies. SSRN Electronic Journal. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3247865

  • Artificial Intelligence and Machine Learning

    • Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press.

    • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. https://www.deeplearningbook.org/

    • Chollet, F. (2021). Deep Learning with Python (2nd ed.). Manning Publications.

    • Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language Models are Few-Shot Learners. arXiv preprint arXiv:2005.14165.

    Decentralized Finance and Blockchain

    • Buterin, V. (2014). Ethereum: A Next-Generation Smart Contract and Decentralized Application Platform. https://ethereum.org/en/whitepaper/

    • Adams, H., Zinsmeister, N., & Robinson, D. (2020). Uniswap v2 Core. https://uniswap.org/whitepaper.pdf

    • Schär, F. (2021). Decentralized Finance: On Blockchain- and Smart Contract-Based Financial Markets. Federal Reserve Bank of St. Louis Review, 103(2), 153-174. https://research.stlouisfed.org/publications/review/2021/02/05/decentralized-finance-on-blockchain-and-smart-contract-based-financial-markets

    • Peretz, G., O'Neil, R., & Krowiak, R. (2021). Automated Market Makers and Decentralized Exchanges: A DeFi Primer. Journal of Financial Transformation, 52(1), 47-59.

    Large Language Models and Financial Applications

    • Wu, T., Li, Z., Yang, Y., Huang, Z., Ding, L., Yang, C., ... & Zhao, Z. (2023). BloombergGPT: A Large Language Model for Finance. arXiv preprint arXiv:2303.17564. https://arxiv.org/abs/2303.17564

    • Yang, K., Gan, Z., Pang, P.N., Su, Y., & Dai, X. (2023). FinGPT: Open-Source Financial Large Language Models. arXiv preprint arXiv:2306.06031. https://arxiv.org/abs/2306.06031

    • Wu, C., Raghunathan, A., Zhang, C., Benmohamed, P.R., & Hooi, B. (2023). Trading with Language Models: An Analysis of their Predictive Power and Limitations. arXiv preprint arXiv:2309.12别9. https://arxiv.org/abs/2309.12819

    https://www.ams.org/notices/201405/rnoti-p458.pdf

    This type of liquidation is initiated for active positions which are in profit to minimize risk for market skew and for positions which are in loss to minimize isolated risk for the position. This enables the protocol to mitigate systematic risk such as missed liquidations or an over-leveraged position which may affect the market negatively. This is handled via ADL Engine which may take hold of the position once it reaches the maximum risk factors defined in market, asset or position.

    Let us define the PnL factor for a position in profit, FPnLF_{PnL}FPnL​ using PnL, ApA_pAp​ for the position as

    Since PSP_SPS​ is a constant, hence the relation can be established as

    For any position, we already defined leverage as LPL_PLP​ as

    We already know that for the positions in profit after fees for reference,

    And for positions in loss after fees,

    This can be plotted as

    Considering a 10 USD collateral with maximum leverage of 10X

    If a partial liquidation occurs in any market, it will create an imbalance in that market’s Open Interest which will be balanced by the funding fees skew in subsequent topic. This method of liquidation is often only applicable to the positions with leverage under maximum defined leverage and may pay out profit or left-over collateral.

    Full Liquidation

    When the position’s margin falls the factor defined by the market, it is added in the monitoring queue for the liquidator to execute liquidation of the position. Hence when,

    where FLF_LFL​ is the liquidator fees which is a fixed value in USD. In this method type of liquidation, the position is taken over by the protocol’s liquidator and closed with a loss for the traders and as a gain for the market. This is applicable to all positions having leverage above maximum starting leverage defined by the market or at the price when M+FLM + F_LM+FL​ is less than MPM_PMP​, the position’s margin is under minimum required maintenance margin, which is triggered first.

    FPnL=ApPs,Ap>0F_{\text{PnL}} = \frac{A_p}{P_s}, \quad A_p > 0 FPnL​=Ps​Ap​​,Ap​>0
    FPnL∝AporFPnL=∂Ap,∂=1PS,0<∂<1F_{\text{PnL}} \propto A_p \quad \text{or} \quad F_{\text{PnL}} = \partial A_p, \quad \partial = \frac{1}{P_S}, \quad 0 < \partial < 1 FPnL​∝Ap​orFPnL​=∂Ap​,∂=PS​1​,0<∂<1
    LP=PsCpL_P = \frac{P_s}{C_p} LP​=Cp​Ps​​
    LP=PsCp+ProfitL_P = \frac{P_s}{C_p + \text{Profit}} LP​=Cp​+ProfitPs​​
    LP=PsCp−LossL_P = \frac{P_s}{C_p - \text{Loss}} LP​=Cp​−LossPs​​
    MP<M+FLM_P< M+F_LMP​<M+FL​

    Introduction

    "Get smart people together, give them a lot of freedom, create an atmosphere where everyone talks to everyone else, provide the best infrastructure, and make everyone partners."

    Jim Simons, founder of Renaissance Technologies

    World Fund is a modular AI-powered platform that revolutionizes the creation and management of investment funds in the DeFi ecosystem. By leveraging cutting-edge Large Language Models and machine learning algorithms, World Fund enables users to build trading strategies using natural language, avoid overfitting through rigorous out-of-sample backtesting, and deploy autonomous AI agents that can adapt to changing market conditions.

    Core Features

    • - Build trading strategies through simple conversations

    • - Scientifically validate and optimize strategies while preventing overfitting

    • - Deploy validated strategies through a decoupled event-driven architecture

    Discover how these features work together in our .

    Synergy with World Market

    World Fund is designed for optimal integration with World Market, our purpose-built Perpetual DEX. This synergistic relationship ensures maximum performance, security, and feature compatibility between both platforms.

    This GitBook provides a comprehensive overview of the World Fund platform. For technical details, code implementation, and development resources, please refer to our .

    Fund Builder

    The Fund Builder is a revolutionary component that democratizes access to sophisticated fund creation through natural language interfaces. By removing technical barriers, it enables both experienced fund managers and retail investors to create and deploy trading strategies without programming expertise.

    Natural Language Strategy Creation

    At the core of the Fund Builder is its ability to translate human language into executable trading strategies:

    • Multilingual Support: Users can describe trading strategies in their native language (English, French, Spanish, Chinese, and more)

    • Natural Language Interface: Complex trading ideas can be expressed in everyday language

    • LLM-Powered Code Generation: Advanced AI models translate these descriptions into optimized code using the B3X SDK

    • Interactive Refinement: Users can iteratively refine their strategies through conversational feedback loops

    Strategy Creation Process

    The Fund Builder guides users through a structured strategy creation process:

    1. Strategy Description: User describes their trading idea in natural language

    2. AI Interpretation: System interprets and formalizes the strategy

    3. Parameter Configuration: User sets and adjusts key parameters with AI assistance

    4. Strategy Visualization: System generates visual representations of strategy logic

    User Experience

    The Fund Builder prioritizes accessibility without sacrificing sophistication:

    • No-Code Interface: Complete elimination of coding requirements

    • Strategy Templates: Pre-built templates for common strategy types

    • Educational Guidance: Contextual education on strategy components and financial concepts

    • Risk Assessment: Clear explanation of potential risks and limitations

    Example Interaction

    Initial Strategy Request

    User: "I want to create a strategy that buys Bitcoin when the 50-day moving average crosses above the 200-day moving average, and sells when it crosses below."Fund Builder: "I understand you want to implement a Golden Cross/Death Cross strategy for Bitcoin. Let me design that for you. This strategy will:

    1. Buy BTC when the 50-day MA crosses above the 200-day MA (Golden Cross)

    2. Sell BTC when the 50-day MA crosses below the 200-day MA (Death Cross)

    Would you like to add any filters or additional conditions to this strategy?"

    Strategy Refinement

    User: "Yes, only enter if the volume is above average."Fund Builder: "Great addition. I'll modify the strategy to only trigger entries when:

    1. The 50-day MA crosses above the 200-day MA (Golden Cross), AND

    2. The current volume is above the 20-day average volume

    This should help filter out false signals. Would you like to add a specific position sizing rule or risk management parameter?"

    The Fund Builder guides users through an iterative process, suggesting improvements and asking clarifying questions to refine the strategy. This conversational approach makes sophisticated strategy creation accessible to users without technical expertise.

    Technical Implementation

    Behind its intuitive interface, the Fund Builder leverages sophisticated technology:

    • Strategy Parsing Models: Specialized LLMs trained to understand trading concepts

    • Code Generation Pipeline: Multi-stage process for translating natural language to executable code

    • Validation Circuits: Systems to ensure generated strategies meet technical and risk standards

    • User Intent Analysis: AI models that understand the user's true objectives beyond literal instructions

    Integration Points

    The Fund Builder connects seamlessly with other components in the World Fund ecosystem:

    • Strategies flow directly to the Quant Agent for scientific validation

    • Approved strategies are stored in the Curated Strategy Library

    • Deployed strategies interface with the Signal Generator and Trader Agent for execution

    By combining natural language processing with financial expertise, the Fund Builder creates an unprecedented level of accessibility to sophisticated quantitative trading, empowering users regardless of their technical background.

    World Fund

    An Overview of Economical Model of World Fund

    The World Fund includes a range of fees applicable to its various financial and operational activities. These fees are designed to cover fund operations, align incentives, and ensure efficient capital deployment. The fee structure includes:

    • Vault Creation Fees – Charged when a new vault is created within the World Fund ecosystem.

    • Deposit Fees – Applied when users deposit capital into a World Fund vault.

    • Withdrawal Fees – Incurred when users withdraw funds from a vault.

    • Performance Fees – A percentage of profits generated by the vault, typically allocated to fund managers or the protocol treasury.

    • Management Fees – Recurring fees charged for managing and maintaining the vault and its underlying strategies.

    • Protocol Fees - A fixed or percentage-based fee collected for running the vault operations.

    Fund Manager
    B3X Treasury

    Infrastructure Layer

    The foundation of the World Fund ecosystem provides essential services and tools that support all higher-level components. This layer delivers the technical backbone that enables sophisticated fund creation, management, and execution.

    Trading Tools

    The infrastructure layer includes specialized trading tools:

    • Smart Contracts: Purpose-built contracts for fund creation, capital allocation, and strategy execution

    • Liquidity Pools: Integration with World Market liquidity pools optimized for algorithmic trading

    • Order Execution: Advanced order types and execution algorithms

    • Position Management: Tools for tracking and managing positions across multiple assets

    • Risk Controls: Infrastructure for enforcing risk parameters and circuit breakers

    Curated Strategy Library

    The Curated Strategy Library stores validated trading strategies that have passed rigorous testing:

    • Strategy Repository: Secure storage of validated strategy code and parameters

    • Version Control: Tracking of strategy versions and performance across time

    • Access Controls: Fine-grained permissions for strategy access and modification

    • Component Reuse: Library of building blocks that can be combined to create new strategies

    Quant Tools

    Comprehensive quantitative tools support strategy development, testing, and selection:

    • Backtesting Engine: High-performance system for testing strategies against historical data

    • Out-of-Sample Validation: Tools specifically designed to prevent overfitting

    • Walk-Forward Analysis: Systems for testing strategy robustness across time

    • Regime Analysis: Tools for identifying and testing performance in different market conditions

    Data Infrastructure

    Robust data infrastructure manages the flow of market data and signals:

    • Market Data Feeds: Real-time and historical data from multiple sources

    • On-chain Analytics: Processing and analysis of blockchain data

    • Alternative Data: Integration of sentiment, social, and other non-traditional data sources

    • Data Normalization: Tools for cleaning and standardizing data across sources

    Security Infrastructure

    Comprehensive security systems protect both funds and intellectual property:

    • Secure Agent Wallets: Limited-permission execution wallets for safe strategy operation

    • Multi-signature Controls: Governance systems for critical operations

    • Audit Trails: Complete logging of all system actions for transparency

    • Strategy Encryption: Protection of proprietary trading strategies

    This infrastructure layer provides the solid foundation upon which the entire World Fund ecosystem operates, ensuring reliability, security, and performance at scale.

    Strategy Framework

    The Strategy Framework provides the structure for creating, validating, and executing trading strategies within World Fund. At its core is the Strategy Factory and Strategy Selector (SFSS) system that ensures strategies meet rigorous standards before deployment.

    Strategy Factory and Strategy Selector (SFSS) System

    The SFSS system represents the core architecture for strategy generation, validation, and selection. It follows a structured workflow to ensure only robust, validated strategies reach deployment and are dynamically selected based on current market conditions.

    Execution Layer

    The Execution Layer of World Fund implements a decoupled event-driven architecture that separates strategy processing from order execution. This design creates a clear division of responsibilities, allowing each component to specialize in its specific function.

    Decoupled Event-Driven Architecture

    The execution architecture follows a clear sequence of events:

    World Market

    An Overview of Economical Model of World Market

    Fee Model

    As a global exchange layer, World Market charges the following types of fees, similar to other trading venues:

    • Trading Fees

    Backtesting Preview: Initial backtesting results are presented for review

  • Refinement Dialog: User and AI engage in iterative improvement

  • Validation Handoff: Completed strategy is sent to the Quant Agent for rigorous validation

  • Historical Analogies: Comparison to similar historical strategies for context

    Performance Tracking: Historical data on strategy performance across different market regimes

    Monte Carlo Simulation: Probabilistic testing of strategy performance under various scenarios

  • Parameter Optimization: Tools for finding optimal strategy parameters while avoiding overfitting

  • Feature Engineering: Systems for creating meaningful inputs for strategies

    Circuit Breakers: Automated systems to halt trading under extreme conditions

    Strategy Factory

    The Strategy Factory is responsible for strategy creation through multiple pathways:

    • User-Defined Strategies: Created through the Fund Builder's natural language interface

    • Quant Agent Generation: AI-generated strategies based on market patterns and opportunities

    • Template Modification: Customization of pre-existing strategy templates

    • Expert Design: Manually coded strategies by professional quantitative analysts

    Strategy Selector

    The Strategy Selector dynamically chooses the most appropriate strategies based on current market conditions, optimizing performance across different regimes:

    • Market Regime Detection: Identifies distinct market environments (trending, ranging, volatile) using a combination of statistical pattern recognition and machine learning

    • Dynamic Strategy Allocation: Automatically adjusts capital allocation across strategies based on their historical performance in similar market conditions

    The Strategy Selector uses machine learning to dynamically allocate capital across the strategy pool based on recent performance and detected market regimes.

    The allocation process works as follows:

    1. Historical performance of each strategy is analyzed across different market conditions

    2. Market regime detection identifies the current market environment

    3. An optimal allocation of weights is calculated for the upcoming period

    This process can be represented mathematically as follows:

    Given performance sti of strategy i at time t\text{Given performance } s^i_t \text{ of strategy } i \text{ at time } tGiven performance sti​ of strategy i at time tCalculate weights (w1,w2,…,wn) for period [T,T+1]\text{Calculate weights } (w_1, w_2, \ldots, w_n) \text{ for period } [T, T+1]Calculate weights (w1​,w2​,…,wn​) for period [T,T+1]Subject to: 0≤wj≤1 and ∑j=1nwj≤1\text{Subject to: } 0 \leq w_j \leq 1 \text{ and } \sum_{j=1}^{n} w_j \leq 1Subject to: 0≤wj​≤1 and ∑j=1n​wj​≤1

    • Performance Metrics: Comprehensive evaluation beyond simple returns using a multi-factor analysis framework (Sharpe, Sortino, Calmar ratios, drawdowns, recovery periods, etc.)

    • Robustness Tests: Implements walk-forward analysis, Monte Carlo simulation with over 1,000 iterations, and stress testing against historical market crashes

    • Market Regime Analysis: Segments and evaluates performance across different market conditions using hierarchical clustering and regime-switching models

    • Correlation Assessment: Utilizes advanced statistical techniques to measure strategy uniqueness compared to existing library, enforcing maximum correlation thresholds

    • Risk Profile Validation: Ensures strategy risk characteristics match stated objectives through multi-dimensional risk assessment

    Example Validated Strategies

    The Strategy Framework has validated several sophisticated strategies, including:

    • Adaptive Moving Average Crossover: A strategy that dynamically adjusts moving average periods based on market volatility, validated across bull, bear, and sideways markets since 2020. This strategy automatically determines optimal MA periods using a proprietary volatility ratio, preventing both excessive trading in high-volatility environments and missed opportunities in low-volatility periods.

    • Volatility Breakout with Volume Confirmation: Detects price breakouts from consolidation patterns, confirmed by abnormal trading volume, with proven effectiveness in range-bound to trending transitions. This approach uses a combination of Bollinger Band width contraction followed by expansion, coupled with volume surge filters to minimize false breakouts.

    • Multi-Timeframe Momentum: Analyzes momentum across multiple timeframes (hourly, daily, weekly) to generate high-conviction entry signals with clearly defined risk parameters. This strategy requires momentum alignment across at least two timeframes, utilizing RSI, MACD, and proprietary momentum oscillators with regime-specific thresholds.

    Decoupled Execution Architecture

    The Strategy Framework implements a decoupled event-driven architecture for strategy execution:

    Signal Generator

    The Signal Generator processes validated strategies and generates trading signals:

    • Receives market data and on-chain events in real-time

    • Applies strategy logic to generate precise trading signals

    • Calculates position sizing and risk parameters

    • Emits structured signal events to the execution layer

    Trader Agent

    The Trader Agent focuses exclusively on optimizing order execution:

    • Receives signal events from the Signal Generator

    • Determines optimal execution approach based on market conditions

    • Manages slippage and minimizes market impact

    • Handles position entry, modification, and exit

    • Reports execution quality metrics back to the system

    This complete separation between strategy processing (Signal Generator) and order execution (Trader Agent) allows each component to specialize in its specific function, creating more efficient and reliable performance.

    Strategy Representation

    Strategies in the framework are represented through a standardized format:

    • Metadata: Strategy identification, version, creator, and description

    • Parameters: Configurable inputs with valid ranges and defaults

    • Logic Definition: The core algorithm expressed in a standardized format

    • Risk Parameters: Defined risk controls including position sizing, stop-loss, and exposure limits

    • Market Requirements: Specific data inputs and market conditions needed for proper execution

    This comprehensive Strategy Framework creates a complete ecosystem for strategy development, validation, and that only well-tested strategies with genuine edge reach deployment while maintaining a clear separation of concerns between signal generation and trade execution.

    Taker, Market Fees & Rebates

  • Liquidity Provider (LP) Fees

  • Liquidation Fees

  • In addition, World Market imposes certain management fees which directly goes to B3X, including:

    • Asset Addition Fee

    • Market Creation Fee

    • Add/Update Listing Fee

    • Vault Creation Fee

    Trading Fees

    Trading fees are charged when a user places a trade order on World Market Pool. These fees typically vary depending on the specific market in which the user is trading.

    All markets charge the following types of fees, each influenced by an associated impact factor:

    • Opening Fee

    • Closing Fee

    These fees also cover related actions such as collateral deposits and collateral withdrawals.

    Allocation
    Percentage of Total Trading Fees

    Liquidity Providers

    70%

    B3X Stakers

    20%

    B3X Treasury

    10%

    Taker, Maker Fees & Rebates

    When users trade on the World Market Orderbook, they are subject to the following fees based on the nature of the order placed:

    • Maker Fees

    • Taker Fees

    Taker Fees are typically fixed and apply when a user places an order that is immediately matched with an existing order—thus removing liquidity from the market.

    Maker Fees, on the other hand, are designed to incentivize users who add liquidity by placing limit orders that rest on the orderbook. These fees may be lower or even negative (rebates), depending on the quality of the order, such as:

    • Tighter spreads

    • Lower slippage

    This fee structure encourages deeper liquidity and more efficient markets.

    Allocation
    Percentage of Net Taker Fees

    DMM Vault Liquidity Providers

    70%

    DMM Party

    20%

    B3X Treasury

    10%

    Liquidity Provider Fees

    Users incur the following fees when interacting with World Market Pools, the Insurance Fund, and DMM Vaults:

    • Deposit Fee – Charged when users add liquidity to a pool, contribute to the insurance fund, or deposit into a DMM Vault.

    • Withdrawal Fee – Charged when users remove funds from any of the above mechanisms.

    These fees help ensure system stability, manage risk, and maintain fair incentives for liquidity provisioning across the platform.

    All LP fees are directed to the B3X Treasury, supporting long-term protocol growth and governance-led development initiatives.

    Liquidation Fees

    World Market applies liquidation fees based on the nature of the liquidation event:

    • Partial Liquidation: When a user’s position is partially liquidated, the fees are similar to closing a trade at a loss. In this case, the standard trading fee distribution applies, meaning the fees are shared among relevant stakeholders (e.g., protocol treasury, referrers, etc.).

    • Full Liquidation: In a full liquidation scenario—where the user’s entire position is closed—a fixed liquidation fee is awarded directly to the liquidator. This acts as an incentive for liquidators to maintain system solvency by promptly executing liquidations.

    Management Fees

    90%

    10%

    Protocol Fees

    0

    100%

    Vault Creation Fees

    0

    100%

    Deposit Fees

    90%

    10%

    Withdrawal Fees

    90%

    10%

    Performance Fees

    90%

    10%

    https://arxiv.org/abs/2005.14165
    Natural Language Strategy Creation
    Intelligent Quant Agent
    Autonomous Execution
    comprehensive architecture
    GitHub repository
    Strategy Processing: Validated strategies are processed by the Signal Generator
  • Signal Generation: When strategy conditions are met, precise trading signals are generated

  • Event Emission: Signals are emitted as structured events to the execution system

  • Order Execution: The Trader Agent receives signals and optimizes execution

  • Position Management: Positions are established and managed according to the strategy

  • Signal Generator

    The Signal Generator focuses exclusively on strategy logic and signal generation:

    • Market Data Processing: Ingests and processes real-time market data

    • Strategy Application: Applies validated strategy logic to current market conditions

    • Signal Calculation: Determines precise entry/exit points and position sizing

    • Risk Parameter Application: Applies strategy-specific risk controls

    • Event Creation: Generates standardized signal events with complete execution instructions

    Signal Types

    The Signal Generator can emit various types of signals:

    • Entry Signals: Instructions to establish new positions

    • Exit Signals: Instructions to close existing positions

    • Adjustment Signals: Instructions to modify position parameters (size, stops, etc.)

    • Hedge Signals: Instructions to establish offsetting positions for risk management

    Trader Agent

    The Trader Agent focuses exclusively on optimal order execution:

    • Order Type Selection: Chooses between market, limit, and advanced order types

    • Execution Timing: Determines optimal timing based on market conditions

    • Order Splitting: Breaks large orders into smaller pieces to minimize impact

    • Venue Selection: Routes orders to optimal venues for best execution

    • Slippage Management: Implements techniques to minimize execution slippage

    • Transaction Cost Analysis: Monitors and reports on execution quality

    Benefits of Decoupled Architecture

    This separation of concerns provides significant advantages:

    • Specialization: Each component can focus on its specific role without compromise

    • Independent Scaling: Components can scale independently based on their specific requirements

    • Failure Isolation: Issues in one component don't necessarily affect others

    • Optimized Performance: Each component can be optimized for its specific function

    • Enhanced Testing: Components can be tested independently with simulated inputs

    By separating signal generation from order execution, World Fund achieves both high-quality strategy processing and optimal trade execution without sacrificing either.

    Integration with World Market

    The Execution Layer is specifically designed for optimal integration with World Market:

    • Priority Execution: Special execution channels for World Fund strategies

    • Optimized Order Types: Custom order types designed specifically for algorithmic trading

    • Enhanced Liquidity Access: Privileged access to World Market liquidity pools

    • Reduced Latency: Optimized communication paths between World Fund and World Market

    • Unified Risk Management: Coordinated risk controls across both platforms

    This purpose-built integration between World Fund and World Market creates a seamless execution environment that surpasses what would be possible with generic third-party connections.

    Security and Monitoring

    The Execution Layer includes comprehensive security and monitoring features:

    • Real-time Monitoring: Continuous tracking of signal generation and execution

    • Performance Analytics: Detailed analysis of execution quality and slippage

    • Anomaly Detection: Systems to identify unusual patterns or potential issues

    • Circuit Breakers: Automatic safeguards that trigger under extreme conditions

    • Audit Trail: Complete logging of all signals and executions for transparency

    The Execution Layer represents a significant advancement in trading architecture, creating a system where strategy intelligence and execution efficiency both reach their full potential through clear separation of concerns and specialized optimization.

    Execution Architecture

    User Layer

    At the top level of the World Fund architecture, the User Layer serves as the interface for three primary user types, each with distinct needs and objectives.

    User Types

    Traders

    Traders interact directly with the Perp DEX for trading activities. They benefit from:

    • Direct market access with advanced order types

    • Integration with trading tools and interfaces

    • Real-time market data and analytics

    Investors

    Investors allocate capital to funds and monitor performance. Their primary capabilities include:

    • Portfolio allocation across multiple funds

    • Performance monitoring and analytics

    • Risk assessment tools

    • Seamless entry and exit from fund positions

    Fund Managers

    Fund managers create and manage investment strategies. They leverage:

    • Strategy creation and optimization tools

    • Performance analytics and reporting

    • Capital raising capabilities

    • Risk management systems

    Interface Design

    The User Layer provides specialized interfaces tailored to each user type's specific needs:

    • Intuitive Dashboards: Each user type accesses dashboards designed specifically for their use case

    • Unified Experience: Despite different capabilities, all interfaces maintain consistent design principles

    • Mobile and Desktop Support: Full functionality across devices

    • Customizable Views: Users can configure their experience based on personal preferences

    Integration Points

    The User Layer connects with the underlying application layers through:

    • API endpoints for programmatic access

    • Event subscriptions for real-time updates

    • Authentication and permission management

    • Data visualization components

    This comprehensive interface layer ensures that all users—whether they are sophisticated traders, passive investors, or professional fund managers—can access the capabilities of World Fund in a way that matches their specific needs and expertise level.

    Purposeful Stablecoins

    Endless Stablecoins, Limited Purpose — It’s Time to Redefine Utility.

    Currently, there are over 10+ stablecoins with a supply exceeding $100M. Yet, USDT powers nearly all CEX perps, while USDC dominates DEX perps. The other 10+ stablecoins have minimal utility or buying power in both spot and perps markets. It’s time to change that.

    With the World Market, all stablecoins finally get the DeFi boost they have been waiting for.

    Short-Only Vault

    The Short-Only Vault Module allows users to create vaults that exclusively hold short positions based on the collateral deposited.

    If you’re convinced that an asset will collapse, like how GCR did with Luna, you can launch a short-only vault and invite others to join your vault.

    Together, you can launch markets on World Market using the vault tokens to further amplify your strategy. Whether you’re betting on a downfall or riding a wave up, World Market is designed to support all strategies — positive or negative.

    Quant Agent

    The Quant Agent is the central intelligence engine of World Fund, responsible for generating, testing, and optimizing trading strategies through rigorous scientific methodologies. Unlike conventional strategy development approaches, the Quant Agent systematically addresses overfitting—ensuring strategies perform well across different market conditions, not just in historical data.

    Scientific Methodology

    The Quant Agent employs a comprehensive scientific approach to strategy development:

    • Hypothesis-Driven Development: Strategies are created based on well-defined financial hypotheses

    • Rigorous Testing Framework: Multiple validation methods to verify strategy robustness

    • Out-of-Sample Validation: Systematic evaluation of strategies on data not used in development

    • Walk-Forward Analysis: Testing strategy performance across rolling time windows

    • Monte Carlo Simulation: Probabilistic assessment of strategy performance under various scenarios

    MCP Integration

    The Quant Agent leverages the Model Context Protocol (MCP) to extend its capabilities through an open ecosystem of specialized tools:

    • Data Providers: Access to market data, on-chain analytics, and alternative data sources

    • Analytical Tools: Specialized statistical and mathematical tools for strategy analysis

    • Specialized AI Models: Integration with domain-specific AI systems for enhanced capabilities

    • Market Simulators: Advanced market simulation for realistic strategy testing

    The Model Context Protocol (MCP) enables the Quant Agent to access specialized capabilities without having to rebuild them internally, creating an extensible platform that can evolve with the ecosystem.

    Strategy Generation Capabilities

    The Quant Agent can generate a wide range of strategies across different approaches:

    • Technical Analysis: Pattern recognition, indicator-based strategies, and price action techniques

    • Statistical Arbitrage: Mean reversion, pairs trading, and statistical edge detection

    • Machine Learning: Predictive models, clustering, and classification-based approaches

    • On-chain Analysis: Strategies based on blockchain data and network metrics

    The sentiment analysis process can be mathematically expressed as:

    Where:

    Scientific Overfitting Prevention

    A core strength of the Quant Agent is its systematic approach to preventing overfitting through advanced scientific methodologies:

    • Cross-Validation: Testing strategies across different market regimes and time periods using k-fold and time-based validation techniques

    • Complexity Penalization: Applying Occam's razor through regularization techniques (L1, L2, elastic net) that mathematically penalize excessive complexity

    • Dimensionality Reduction: Focusing on truly impactful variables through Principal Component Analysis (PCA) and feature importance ranking

    Time Series Forecasting

    World Fund leverages advanced time series forecasting techniques to predict market movements. The general form of our time series forecasting model using Large Language Models can be expressed as:

    Where:

    Our time series forecasting component uses transformer architecture to analyze historical price data and predict future market movements. The model is trained to minimize the mean squared error (MSE) between the predicted and actual values:

    Where:

    Optimization Framework

    The Quant Agent includes a sophisticated optimization framework that improves strategies while guarding against curve-fitting:

    • Parameter Tuning: Automated discovery of optimal parameter combinations with regularization

    • Feature Engineering: Identification of relevant market signals using information gain metrics

    • Strategy Hybridization: Combining successful strategies to create more robust composite approaches

    • Weakness Identification: Pinpointing specific market conditions where strategies underperform

    Out-of-Sample Backtesting Methodology

    World Fund employs rigorous validation techniques to prevent overfitting and ensure strategy robustness. Building on established quantitative finance principles and seminal research on backtest overfitting, our approach systematically addresses the challenges that lead to misleading backtest results and poor out-of-sample performance.

    Additionally, our AI trading agents utilize a reinforcement learning framework where trading decisions are formulated as a Markov Decision Process (MDP).

    In this reinforcement learning framework:

    • The agent learns a policy that maximizes the expected return

    • Trading decisions are sequentially optimized based on market states and rewards

    The expected return is expressed through the following equation:

    Each component of this equation has the following interpretation:

    This mathematical framework guides our validation approach, which includes:

    • Causal Feature Analysis: Identifying truly predictive features versus coincidental correlations

    • Multiple Hypothesis Testing Correction: Applying statistical methods like Bonferroni, Holm, and False Discovery Rate to account for data mining bias

    • Combinatorial Purged Cross-Validation (CPCV): Advanced technique that addresses the temporal dependence in financial data while ensuring proper validation

    • Statistical Significance Validation

    Iterative Strategy Optimization

    Strategies undergo continuous improvement through an AI-driven optimization process. Our AI trading agents utilize reinforcement learning algorithms to optimize trading strategies. These agents are trained using historical trading data and simulated environments to learn policies that maximize returns.

    The agents employ methods such as Q-learning and policy gradient approaches to update their strategies based on observed rewards. The Q-value update rule in Q-learning is given by:

    Where:

    Continuous Learning

    Beyond initial strategy development, the Quant Agent continuously learns and improves:

    • Performance Monitoring: Tracking strategy performance against expectations

    • Regime Detection: Identifying shifts in market conditions that may affect strategy performance

    • Adaptation: Adjusting strategies based on evolving market dynamics

    • Knowledge Accumulation: Building on insights from previous strategy generations

    The Quant Agent represents a significant advancement in quantitative trading by combining the power of artificial intelligence with the rigor of scientific methodology, creating a system that can generate and validate trading strategies with unprecedented reliability and robustness.

    Outdated DeFi Perps Offerings

    DeFi Derivatives: Stuck in the Past While CEXs Dominate

    DeFi has always been at the forefront of innovation — exploring pre-markets, prediction markets, time-trading, and social trading, this year. Yet, derivatives remain stagnant, with no significant asset listings compelling users to leave CEXs and trade on DEXs. This lack of ambition in asset offerings fails to attract both CEX traders and non-crypto-native users.

    If we want to compete, we must step up and revolutionize market offerings. DeFi needs to deliver markets so enticing and comprehensive that traders are not just drawn to DEXs — they are compelled to stay.

    Just like DEXes, perpetual futures DEXes should be first to list new market offerings especially when LPs are willing to take the risk.

    Price Protection

    Several price protection mechanisms have been implemented in the off-chain and on-chain infrastructure to ensure robust, tamperproof, fair and transparent pricing for all the end-users. Some of them have been mentioned below:

    Price Manipulation Protection

    There have been cases where a few market participants have manipulated the price and generated profits. On the other hand, there have been several oracle attacks across DeFi each year resulting in loss of millions of dollars of users' assets.

    To address such issues, B3X will use a black box function to ensure tamper-proof pseudo-deterministic price for fair trade execution. This function takes a real world source as seed which is consistently changing and generates a random number using Mersenne Twister, a pseudo-random number generator.

    Sentiment Analysis: Natural language processing of news, social media, and financial reports

    Parameter Stability Analysis
    : Ensuring strategy performance isn't dependent on specific parameters through sensitivity analysis and robustness metrics
  • Walk-Forward Analysis: Implementing time-based data partitioning with anchored and expanding window methodologies

  • Ensemble Methods: Combining diverse strategy approaches to reduce model-specific overfitting risk, including bagging, boosting, and stacking techniques

  • Robustness Testing: Evaluating performance under different market conditions and scenarios through stress testing and regime analysis

  • Statistical Significance: Rigorous testing of results against null hypotheses with appropriate corrections for multiple hypothesis testing

  • : Using methods like White's Reality Check and Hansen's Superior Predictive Ability test to verify results
    y^=softmax(W⋅ReLU(U⋅h+b1)+b2)\hat{y} = \text{softmax}(W \cdot \text{ReLU}(U \cdot h + b_1) + b_2)y^​=softmax(W⋅ReLU(U⋅h+b1​)+b2​)
    h : Hidden state of the Large Language Modelh \text{ : Hidden state of the Large Language Model}h : Hidden state of the Large Language Model
    U,W : Weight matricesU, W \text{ : Weight matrices}U,W : Weight matrices
    b1,b2 : Bias termsb_1, b_2 \text{ : Bias terms}b1​,b2​ : Bias terms
    y^ : Predicted sentiment score\hat{y} \text{ : Predicted sentiment score}y^​ : Predicted sentiment score
    y^t+h=f(yt,yt−1,…,yt−n;θ)\hat{y}_{t+h} = f(y_{t}, y_{t-1}, \ldots, y_{t-n}; \theta)y^​t+h​=f(yt​,yt−1​,…,yt−n​;θ)
    y^t+h : Forecasted value at time t+h\hat{y}_{t+h} \text{ : Forecasted value at time } t+hy^​t+h​ : Forecasted value at time t+h
    yt : Observed values at time ty_t \text{ : Observed values at time } tyt​ : Observed values at time t
    θ : Parameters of the model\theta \text{ : Parameters of the model}θ : Parameters of the model
    MSE=1n∑i=1n(y^i−yi)2\text{MSE} = \frac{1}{n} \sum_{i=1}^{n} (\hat{y}_i - y_i)^2MSE=n1​∑i=1n​(y^​i​−yi​)2
    y^i : Predicted values\hat{y}_i \text{ : Predicted values}y^​i​ : Predicted values
    yi : Actual valuesy_i \text{ : Actual values}yi​ : Actual values
    R=E[∑t=0Tγtrt]R = \mathbb{E}\left[\sum_{t=0}^{T}\gamma^t r_t\right]R=E[∑t=0T​γtrt​]
    R : Expected return that the agent aims to maximizeR \text{ : Expected return that the agent aims to maximize}R : Expected return that the agent aims to maximize
    rt : Reward received at time step tr_t \text{ : Reward received at time step } trt​ : Reward received at time step t
    γ : Discount factor that balances immediate versus future rewards\gamma \text{ : Discount factor that balances immediate versus future rewards}γ : Discount factor that balances immediate versus future rewards
    T : Time horizon over which rewards are accumulatedT \text{ : Time horizon over which rewards are accumulated}T : Time horizon over which rewards are accumulated
    Q(s,a)←Q(s,a)+α(r+γmax⁡a′Q(s′,a′)−Q(s,a))Q(s, a) \leftarrow Q(s, a) + \alpha \left( r + \gamma \max_{a'} Q(s', a') - Q(s, a) \right)Q(s,a)←Q(s,a)+α(r+γmaxa′​Q(s′,a′)−Q(s,a))
    Q(s,a) : Q-value for state s and action aQ(s, a) \text{ : Q-value for state } s \text{ and action } aQ(s,a) : Q-value for state s and action a
    α : Learning rate\alpha \text{ : Learning rate}α : Learning rate
    r : Rewardr \text{ : Reward}r : Reward
    γ : Discount factor\gamma \text{ : Discount factor}γ : Discount factor
    s′,a′ : Next state and actions', a' \text{ : Next state and action}s′,a′ : Next state and action
    Quant Agent Cycle
    Price Source Deviation Check

    The prices of all the real-world and decentralized sources are checked for deviations as defined in the asset manager for the asset, and such factor is called Deviation Factor, DfD_{f}Df​which can be unique for each asset.

    Let nnn be the number of the real-world sources with prices, P1,P2,....,PnP_{1}, P_{2},....,P_{n}P1​,P2​,....,Pn​ and PdP_{d} Pd​ be the price from a decentralized source such as Chainlink or Pyth, then if

    then ithithith price source is valid and acceptable and will be considered for final price computation.

    Sample Price Feed for BTC/USD:

    Binance: 45125.89, OKX: 45100.45, Coinbase: 45156.34, MEXC: 45900.90, Kucoin: 45146.22, Bybit: 45116.78, Chainlink: 45110.45, Pyth: 45111.23

    In this sample, MEXC's BTC price is out of acceptable deviation (>1.5%) as compared to decentralized sources, hence will be rejected.

    Price Source Outlier Check

    Once all the real-world sources pass the deviation check, the off-chain infrastructure checks all the prices from these sources for outliers to ensure fair pricing for all.

    In order to process this, we can define deviations of 1st1st1st price feed against other n−1n -1n−1 sources, as

    Hence, the deviation of 1st1st1st price feed against others can be written as D1−2,D1−3,....,D1−nD_{1-2}, D_{1-3},....,D_{1-n}D1−2​,D1−3​,....,D1−n​ and similarly for 2nd2nd 2nd price feed, we can define D2−1,...,D2−nD_{2-1},...,D_{2-n}D2−1​,...,D2−n​ and so on.

    Then we compute variance of this dataset to fine-tune the sources, as

    The maximum acceptable value of VVVis defined in the Asset Manager for an asset. If the VVVis not under acceptable value, the dataset is sorted in ascending order and the first and last element is removed. This process is continued until V is under acceptable value. One must note that with each elimination, the underlying price feed is also eliminated and not considered from final computation.

    In the previous example, if MEXC's price feed by any chance passes the deviation check, it will fail in the outlier check since the deviations of MEXC's price feed will be highest amongst other feeds.

    Price Feed Fault Check

    Since FTX Saga and several API incidents [2], it is important to implement fault checks for the price feed sources.

    B3X deploys an additional check of the price feed sources to monitor their uptime. Let a price feed report price, PtP_tPt​ at time ttt then the off-chain infrastructure computes, RfR_fRf​, relative price difference as

    If Rf=0R_f = 0Rf​=0, the price feed is considered faulty, invalid or dead, and hence will not be included to compute final off-chain price. But this check depends upon the asset, some asset may skip the fault check for example: RWA assets on off-market hours.

    [1]
    Pi−PdPd<Df\frac{P_{i}-P_{d}}{{P_{d}}} < D_{f}Pd​Pi​−Pd​​<Df​
    D1−i=Pi−P1P1D_{1-i} = \frac{P_{i}-P_{1}}{P_{1}} D1−i​=P1​Pi​−P1​​
    V=σ2=1J∑j=1n(Dj−σ)2V = \sigma^2 = \frac{1}{J} \sum_{j=1}^n (D_j - \sigma)^2V=σ2=J1​j=1∑n​(Dj​−σ)2
    Rf=Pt−Pt−1Pt−1R_f = \frac{P_t-P_{t-1}}{P_{t-1}}Rf​=Pt−1​Pt​−Pt−1​​

    Market Management

    One of the core principles of the protocol to democratize market creation for spot and futures product on the decentralized finance ecosystem. This can be achieved by implementing this principle at the core of the smart contracts. Any user can request market creation after getting their asset whitelist to become spot and futures liquidity provider in the protocol. The steps to achieve permissionless market creation can be summarized as follows:

    1. Get minimum of one asset to be whitelisted as a market asset.

    2. Create market using the whitelisted asset as collateral.

    3. Add liquidity to the newly created market to start trading.

    4. Perform swap or opening a position.